ndwarshuis
/
org-mode
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Refactor unescaping functions 

* org.el (org-link-unescape): Simpler algorithm for replacing percent
escapes.
(org-link-unescape-compound): Use cond statements instead of nested
if, convert hex string with string-to-number, save match data.
(org-link-unescape-single-byte-sequence): Use mapconcat and
string-to-number for unescaping single byte sequence.
This commit is contained in:
David Maus 2010-11-27 20:02:23 +01:00
parent dc76fd5d71
commit 7b58cccddd
1 changed files with 39 additions and 63 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

102
lisp/org.el
View File

@ -8642,77 +8642,53 @@ If optional argument MERGE is set, merge TABLE into
(defun org-link-unescape (str)
"Unhex hexified unicode strings as returned from the JavaScript function
encodeURIComponent. E.g. `%C3%B6' is the german Umlaut `ö'."
(setq str (or str ""))
(let ((tmp "")
(case-fold-search t))
(while (string-match "\\(%[0-9a-f][0-9a-f]\\)+" str)
(let* ((start (match-beginning 0))
(end (match-end 0))
(hex (match-string 0 str))
(replacement (org-link-unescape-compound (upcase hex))))
(setq tmp (concat tmp (substring str 0 start) replacement))
(setq str (substring str end))))
(setq tmp (concat tmp str))
tmp))
(unless (and (null str) (string= "" str))
(let ((pos 0) (case-fold-search t) unhexed)
(while (setq pos (string-match "\\(%[0-9a-f][0-9a-f]\\)+" str pos))
(setq unhexed (org-link-unescape-compound (match-string 0 str)))
(setq str (replace-match unhexed t t str))
(setq pos (+ pos (length unhexed))))))
str)
(defun org-link-unescape-compound (hex)
"Unhexify unicode hex-chars. E.g. `%C3%B6' is the German Umlaut `ö'.
Note: this function also decodes single byte encodings like
`%E1' (\"á\") if not followed by another `%[A-F0-9]{2}' group."
(let* ((bytes (remove "" (split-string hex "%")))
(ret "")
(eat 0)
(sum 0))
(while bytes
(let* ((b (pop bytes))
(a (elt b 0))
(b (elt b 1))
(c1 (if (> a ?9) (+ 10 (- a ?A)) (- a ?0)))
(c2 (if (> b ?9) (+ 10 (- b ?A)) (- b ?0)))
(val (+ (lsh c1 4) c2))
(shift
(if (= 0 eat) ;; new byte
(if (>= val 252) 6
(if (>= val 248) 5
(if (>= val 240) 4
(if (>= val 224) 3
(if (>= val 192) 2 0)))))
6))
(xor
(if (= 0 eat) ;; new byte
(if (>= val 252) 252
(if (>= val 248) 248
(if (>= val 240) 240
(if (>= val 224) 224
(if (>= val 192) 192 0)))))
128)))
(if (>= val 192) (setq eat shift))
(setq val (logxor val xor))
(setq sum (+ (lsh sum shift) val))
(if (> eat 0) (setq eat (- eat 1)))
(cond
((= 0 eat) ;multi byte
(setq ret (concat ret (org-char-to-string sum)))
(setq sum 0))
((not bytes) ; single byte(s)
(setq ret (org-link-unescape-single-byte-sequence hex))))
)) ;; end (while bytes
ret ))
(save-match-data
(let* ((bytes (cdr (split-string hex "%")))
(ret "")
(eat 0)
(sum 0))
(while bytes
(let* ((val (string-to-number (pop bytes) 16))
(shift-xor
(if (= 0 eat)
(cond
((>= val 252) (cons 6 252))
((>= val 248) (cons 5 248))
((>= val 240) (cons 4 240))
((>= val 224) (cons 3 224))
((>= val 192) (cons 2 192))
(t (cons 0 0)))
(cons 6 128))))
(if (>= val 192) (setq eat (car shift-xor)))
(setq val (logxor val (cdr shift-xor)))
(setq sum (+ (lsh sum (car shift-xor)) val))
(if (> eat 0) (setq eat (- eat 1)))
(cond
((= 0 eat) ;multi byte
(setq ret (concat ret (org-char-to-string sum)))
(setq sum 0))
((not bytes) ; single byte(s)
(setq ret (org-link-unescape-single-byte-sequence hex))))
)) ;; end (while bytes
ret )))
(defun org-link-unescape-single-byte-sequence (hex)
"Unhexify hex-encoded single byte character sequences."
(let ((bytes (remove "" (split-string hex "%")))
(ret ""))
(while bytes
(let* ((b (pop bytes))
(a (elt b 0))
(b (elt b 1))
(c1 (if (> a ?9) (+ 10 (- a ?A)) (- a ?0)))
(c2 (if (> b ?9) (+ 10 (- b ?A)) (- b ?0))))
(setq ret
(concat ret (char-to-string
(+ (lsh c1 4) c2))))))
ret))
(mapconcat (lambda (byte)
(char-to-string (string-to-number byte 16)))
(cdr (split-string hex "%")) ""))
(defun org-xor (a b)
"Exclusive or."